Dockerfile

# Official Python image (non-slim for better compatibility)
FROM python:3.12-bullseye

# Set environment variables
ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1

# Set work directory
WORKDIR /app

# Install system dependencies for OCR & PDF
RUN apt-get update && apt-get install -y \
    poppler-utils \
    tesseract-ocr \
    libgl1 \
    libglib2.0-0 \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements first for caching
COPY requirements.txt .

# Install Python dependencies
RUN pip install --upgrade pip
RUN pip install --no-cache-dir -r requirements.txt

# Copy project code
COPY . .

# Expose FastAPI port
EXPOSE 8000

# Start the FastAPI app
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]